University of Padova, Italy
Ph.D. Physics, February 2015
University of Pisa, Italy
S.M. Physics, April 2011
University of Bologna, Italy
S.B. Physics, October 2008
MIT Plasma Science and Fusion Center (Cambridge, MA), 2016 – present
Research Scientist (2019 - present)
Postdoctoral Associate (2016- January 2019)
- Research on disruptions and disruption warning algorithms through Machine Learning techniques across many different devices, from Alcator C-Mod and DIII-D, to EAST and KSTAR in Asia.
- Realization of real time algorithms, eventually integrated in the Plasma Control System.
- Leader of MIT-PSFC Machine Learning Working Group.
UniCredit Business Integrated Solutions S.C.p.A., Milan, Italy, 2015 –2016
- Data Scientist in UBIS ScpA in the Big Data group. Worked on Big Data demands from ideation, proof of value to delivery process and contributed to create statistical models that responded to specific business needs, such as Customer Relationship Management. Developed innovative data analysis solutions through advanced statistics and Machine Learning.
Consorzio RFX, National Research Council (CNR), Padua, Italy, 2012 – 2015
PhD student and Research Scientist
- Investigated local transport properties and their modulation depending on the magnetic topology in presence of externally applied magnetic perturbations. Studied the effects that relaxation events inside the plasma have on its boundary topology. Analysis were conducted on RFX-mod. The link between magnetic topology and local transport measurements was explored through a field line tracing code.
- Installation and analysis of data coming from the ExB probe, previously used on COMPASS and ASDEX-Upgrade.
Institute of Plasma Physics, CAS CR, Prague, Czech Republic, May 2014
Visiting Research Scientist
- One-month collaboration project under the Work Package ER-01/ENEA_RFX-02 “Magnetic reconnection in fusion plasmas”, approved by the EUROFUSION organization. Analysis of measurements of ion temperature profile coming from the ExB probe installed on COMPASS.
University of Pisa , Master Thesis, 2018 – 2011
- Development of a transfer model, by studying a two neutron process taking place in the reaction 13C(18O,16O)15C at 84 MeV incident beam energy. The experiment was realized using the large acceptance magnetic spectrometer MAGNEX, at LNS ("Laboratori Nazionali del Sud") laboratories.
- Theoretical calculations were consistent with the experimental data and capable of describing the background that lays below the resonances by considering only the elastic part of the transfer to the continuum reaction: 14C(17O,16O)15C.
- C. Rea et al. “A Real-Time Machine Learning-Based Disruption Predictor on DIII-D”, Nuclear Fusion 59 (2019) 096016 doi: https://doi.org/10.1088/1741-4326/ab28bf
- K.J. Montes, C. Rea et al. “Machine learning for disruption warning on Alcator C-Mod, DIII-D, and EAST”, Nuclear Fusion 59 (2019) 096015 doi: https://doi.org/10.1088/1741-4326/ab1df4
- R.A. Tinguely, K.J. Montes, C. Rea, et al. “An application of survival analysis to disruption prediction via Random Forests”, Plasma Physics and Controlled Fusion 61 (2019) 095009 doi: https://doi.org/10.1088/1361-6587/ab32fc
- C. Rea et al. “Disruption prediction investigations using Machine Learning tools on DIII-D and Alcator C-Mod”, Plasma Physics and Controlled Fusion 60 (2018) 084004 doi: https://doi.org/10.1088/1361-6587/aac7fe
- C. Rea and R.S. Granetz, “Exploratory Machine Learning studies for disruption prediction using large databases on DIII-D”, Fusion Science and Technology 74:1-2, 89-100 (2018) doi: 10.1080/15361055.2017.1407206
- I.L. Danesi and C. Rea, “A Customer Relationship Management Case Study Based on Banking Data” In: Pardalos P., Conca P., Giuffrida G., Nicosia G. (eds) Machine Learning, Optimization, and Big Data. MOD 2016. Lecture Notes in Computer Science, vol 10122. Springer, Cham (2016)
- C. Rea et al., “Comparative studies of electrostatic turbulence induced transport in presence of Resonant Magnetic Perturbations in RFX-mod”, Nuclear Fusion 55 (2015) 113021
- M. Spolaore, M. Agostini, B. Momo, C. Rea et al., “Turbulent electromagnetic filaments in actively modulated toroidal plasma edge”, Nuclear Fusion 55 (2015) 063041
- N. Vianello, C. Rea et al., “Magnetic perturbations as a viable tool for edge turbulence modification”, Plasma Physics and Controlled Fusion 57 (2015) 014027
- F. Cappuzzello, C. Rea et al., “New structures in the continuum of 15C populated by two-neutron transfer”, Physics Letters B 711 (2012) 347–352
- C. Rea, R.S. Granetz, R.A. Tinguely, “Analysis of large databases for disruption prediction on DIII-D”, 9th ITER International School, Physics of Disruptions and Control (2017)
- C. Rea and R.S. Granetz, “Exploratory Machine Learning studies for disruption prediction on DIII-D”, 2nd IAEA Technical Meeting on Fusion Data Processing, Validation and Analysis (2017)
- C. Rea, R.S. Granetz, O. Meneghini, “Studies of the DIII-D disruption database using Machine Learning algorithms”, 59th Annual Meeting of the APS Division of Plasma Physics (2017)
- C. Rea, R.S. Granetz, “Investigating disruption prediction with Machine Learning”, 22nd MHD Stability Control Workshop (2017)
- C. Rea et al. “Characterized Disruption Predictions Using Random Forest Feature Contribution Analysis”, 3rd IAEA Technical Meeting on Fusion Data Processing, Validation and Analysis (2019)
- C. Rea et al. “A Machine Learning-based real time disruption predictor on DIII-D”, 60th Annual Meeting of the APS Division of Plasma Physics (2018)
- Organizer of the first Mini-Conference in Machine Learning, Data Science, and Artificial Intelligence in Plasma Research, at the 60th APS-DPP (DPP)
- C. Rea et al. “Initial results of a Machine Learning-based real time disruption predictor on DIII-D”, 45th European Physical Society Conference on Plasma Physics (2018)
Linked in Profile
Google Scholar Profile
Taming fusion with machine learning (MIT News)
Three Questions: Robert Granetz on fusion research (MIT News)